scout-mindset-bias-check_skill

Overview

This skill detects and removes cognitive biases from reasoning to improve forecasting accuracy and intellectual honesty. It helps you shift from a soldier mindset (defending a conclusion) to a scout mindset (mapping reality), producing clearer probabilities and better-calibrated confidence intervals. Use it as a practical toolkit for debiasing forecasts and decisions.

How this skill works

The skill runs targeted checks—reversal tests, scope sensitivity, status-quo audits, confidence-interval calibration, and a full bias checklist—to reveal motivated reasoning and asymmetric evidence standards. For each detected bias it proposes concrete adjustments (e.g., probability shifts, CI widening, or reference-class corrections) and a remediation priority so you can update forecasts systematically. It emphasizes simple heuristics and tests you can apply quickly to any prediction.

When to use it

• When a prediction feels emotional or you notice a strong preference for one outcome
• When you’re stuck at 50/50 or indecisive and want to validate your reasoning
• Before finalizing a forecast that has high stakes or affects you personally
• After an inside-view analysis that relied on specific details and could be biased
• When you and others disagree and you want to diagnose asymmetric standards

Best practices

• Run the reversal test: imagine equivalent evidence favoring the opposite and ask if you’d accept it
• Check scope sensitivity by testing 10× or 100× changes to see if probabilities scale reasonably
• Audit confidence intervals with the surprise test and historical calibration, then widen if overconfident
• Use reference classes by scale (not broad categories) to ground magnitude estimates
• Prioritize detected biases by severity and estimated percentage-point impact before adjusting

Example use cases

• Political forecasting: test whether you’d accept polls that point the other way and adjust for special pleading
• Startup evaluation: check whether funding magnitude changes success probability appropriately
• Policy forecasting: challenge status-quo assumptions by estimating energy required to maintain current rules
• Project timelines: audit CI width after running a premortem and comparing to similar projects
• Team decisions: run a full bias audit when stakeholders give conflicting probability estimates